摘要
为提高永磁直线同步电动机(PMLSM)位置跟踪性能,采用递归函数链模糊神经网络控制(RFLFNN)方法。RFLFNN结合了函数链神经网络(FLNN)和递归模糊神经网络(RFNN)的优点,利用FLNN实现函数扩展,提高系统的非线性逼近能力并对参数进行辨识;RFNN可实时更新调整神经网络的参数值,估计并抑制不确定性因素的影响。实验结果表明,与RFNN相比,该方法极大地改善了PMLSM伺服系统的位置跟踪性能和鲁棒性能。
In order to improve the position tracking performance of permanent magnet linear synchronous motor(PMLSM),the recursive function link fuzzy neural network(RFLFNN)control method was adopted.RFLFNN was combined functional link neural network(FLNN)with recurrent fuzzy neural network(RFNN),FLNN was used to expand functions and improve the non-linear approximation ability of the system and identify parameters.RFLFNN was used to update and adjust the parameters of the neural network in real time to estimate and suppress the influence of uncertainties.The experimental results show that,this method greatly improves the position tracking performance and robust performance of PMLSM servo system compared with RFNN.
作者
刘佳
LIU Jia(North Branch of Customer Service Center of State Grid,Tianjin 300309,China)
出处
《电气传动》
北大核心
2020年第9期83-87,共5页
Electric Drive
关键词
永磁直线同步电动机
位置跟踪
神经网络
不确定性
permanent magnet linear synchronous motor(PMLSM)
position tracking
neural network
uncertainties
